View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity

2026-04-20

AI Summary

This work addresses the challenge of multi-view geometric and semantic inconsistency in text-driven 3D scene editing by proposing a consistency-aware editing framework based on cross-view joint distribution modeling. The approach employs a dual-path mechanism that jointly optimizes structural correspondence and semantic continuity: a projection-guided structural constraint enforces geometric alignment, while block-level semantic propagation preserves cross-view semantic coherence. To enable supervised training, the authors introduce the first paired multi-view 3D editing dataset and integrate differentiable rendering with implicit 3D representations for end-to-end optimization. Experiments demonstrate that the method significantly outperforms existing techniques on complex scenes, achieving high-fidelity and view-consistent text-driven editing results.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Text-driven 3D scene editing has recently attracted increasing attention. Most existing methods follow a render-edit-optimize pipeline, where multi-view images are rendered from a 3D scene, edited with 2D image editors, and then used to optimize the underlying 3D representation. However, cross-view inconsistency remains a major bottleneck. Although recent methods introduce geometric cues, cross-view interactions, or video priors to mitigate this issue, they still largely rely on inference-time synchronization and thus remain limited in robustness and generalization.In this work, we recast multi-view consistent 3D editing from a distributional perspective: 3D scene editing essentially requires a joint distribution modeling across viewpoints.Based on this insight, we propose a view-consistent 3D editing framework that explicitly introduces cross-view dependencies into the editing process. Furthermore, motivated by the observation that structural correspondence and semantic continuity rely on different cross-view cues, we introduce a dual-path consistency mechanism consisting of projection-guided structural guidance and patch-level semantic propagation for effective cross-view editing. Further, we construct a paired multi-view editing dataset that provides reliable supervision for learning cross-view consistency in edited scenes. Extensive experiments demonstrate that our method achieves superior editing performance with precise and consistent views for complex scenes.

Problem

• view consistency
• 3D scene editing
• cross-view inconsistency
• semantic continuity
• structural correspondence

Innovation

• view-consistent 3D editing
• dual-path consistency
• structural correspondence
• semantic continuity
• cross-view dependency